© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154650
    Prev
    Next
    INDEX
    Explanations

    code syntax like quotes and braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Marriage
    0.44
     وین
    0.42
     মু
    0.41
    وث
    0.41
     vin
    0.41
     Arten
    0.40
     Module
    0.40
    只会
    0.40
    如
    0.39
     Россию
    0.39
    POSITIVE LOGITS
    were
    0.47
     modernize
    0.46
     disqualify
    0.45
    summary
    0.44
    addle
    0.43
    gegevens
    0.43
    Were
    0.42
     morphologies
    0.42
    ൦
    0.42
    ம்பிய
    0.41
    Activations Density 0.000%

    No Known Activations